Take Home Exercise 3

VAST Challenge 3

Huang Anni (Singapore Management University)
05-07-2022

The task

With reference to Challenge 3 of VAST Challenge 2022, you are required to reveal the economic of the city of Engagement, Ohio USA by using appropriate static and interactive statistical graphics methods

Introduction

This exercise requires us to apply the skills you had learned in Lesson 1 and Hands-on Exercise 1 to reveal the demographic of the city of Engagement, Ohio USA by using appropriate static statistical graphics methods. The data should be processed by using appropriate tidyverse family of packages and the statistical graphics must be prepared using ggplot2 and its extensions. image

Data Processing

Our data includes two csv files from the VAST data source.

d <- highlight_key(wage)
p <- ggplot(data=d, aes(x=wage, fill=Wage_Group)) +
    geom_histogram(position="dodge",aes(y = ..density..), binwidth=density(wage$wage)$bw) +
  labs(y= 'Density', x= 'Wage',
       title = "Fig1: Wage Distribution",
       subtitle = "Most people get 50 per month")

ggplotly(p)

fig <- plot_ly(total, x = ~date, y = ~coef, type = 'scatter',mode = 'lines+markers')
fig <- fig %>% layout(title = 'Fig 2.Residence\'s living status through time',
                      xaxis = list(title = "Date"),
                      yaxis = list (title = "Spend/Income"))
fig

p<-ggplot(data=total, aes(x=date, y=remain)) +
  geom_bar(stat = "identity", width = 0.5, fill="steelblue") +
  coord_cartesian(ylim = c(0, 160)) + 
  labs(y= 'Total Deposit', x= 'Date',
       title = "Fig3. Trend of Living Standards",
       subtitle = "Highest remaining in 2022-03") +
  geom_text(aes(label = remain), vjust = -1, colour = "black") +
  theme(axis.title.y= element_text(angle=90),
        axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5),
        axis.ticks.x= element_blank(),
        panel.background= element_blank(), 
        axis.line= element_line(color= 'grey'), 
        panel.grid.major.y = element_line(color = "grey",size = 0.5,linetype = 2))
ggplotly(p)

# unique(wage$Wage_Group)
#fig <- plot_ly(wage, x = ~wage, fill = ~Wage_Group ,type = "histogram")

#fig

income <- financial %>%
  filter(category %in% c('Wage', 'RentAdjustment')) %>%
  group_by(participantId) %>%
  summarise(income = sum(amount))

outcome <- financial %>%
  filter(!category %in% c('Wage', 'RentAdjustment')) %>%
  group_by(participantId) %>%
  summarise(outcome = sum(abs(amount)))

comparison <- merge(income, outcome, by='participantId') %>%
  merge(wage, by='participantId')
comparison$ratio <- comparison$outcome / comparison$income

p <- ggplot(comparison, aes(x = ratio, y = Wage_Group)) +
  geom_boxplot()+
  labs(y= 'Wage Group', x= 'Ratio in wage',
       title = "Fig4: Wage Distribution",
       subtitle = "People with low wages tend to spend most of their money")+
  #theme_ridges() + 
  #scale_fill_viridis_d(name = "Quartiles")+
  ggtitle("Fig3: Wage Distribution")+
  theme(plot.title = element_text(size = 12), 
        legend.position = "top")
p


outcome_different_cats <- financial %>%
  filter(!category %in% c('Wage', 'RentAdjustment')) %>%
  group_by(participantId, category) %>%
  summarise(outcome = mean(abs(amount))) %>%
  merge(wage, by='participantId')
outcome_different_cats$ratio <- outcome_different_cats$outcome / outcome_different_cats$wage
outcome_different_cats$labels <- scales::percent(outcome_different_cats$ratio)
# outcome_different_cats
ggplot(outcome_different_cats,aes(x="", y=outcome, fill=category))+
  geom_bar(width = 1, stat = "identity")+
  coord_polar("y", start=0)+
  scale_fill_brewer(palette="Spectral")+
  ggtitle("Category Distribution")+
  labs(fill='category')+
  xlab("") + 
  ylab("Participants")+
  geom_text(aes(label = labels))